Multiple Change Detection Research Articles

An Ensemble Learning Framework for Anomaly Detection of Important Geographical Entities

Abstract. Due to the complex landforms and the limited resolution of remote sensing imagery, it is difficult to avoid the problem of incorrectly capturing geographical entities, such as buildings. Therefore, anomaly detection of important geographical entities is of great significance to ensure the authenticity and accuracy of geographical entity data. In this paper, we propose an ensemble learning framework for anomaly detection of geographical entity by aggregating the predicted labels generated by multiple deep learning models. In detail, we explore multiple change detection and semantic segmentation model and fully utilize the advantages of various deep learning neural network architectures. The proposed anomaly detection strategy of buildings has been performed on two benchmark datasets, including WHU Building change detection dataset and LEVIR building change detection dataset, the experimental results prove that the proposed method can achieve a more robust and better performance than using single change detection model in terms of quantitative performance and visual performance.

Spectrum-Induced Transformer-Based Feature Learning for Multiple Change Detection in Hyperspectral Images

Spectrum-Induced Transformer-Based Feature Learning for Multiple Change Detection in Hyperspectral Images

Collaborative multiple change detection methods for monitoring the spatio-temporal dynamics of mangroves in Beibu Gulf, China

ABSTRACT Mangrove ecosystems are one of the most diverse and productive marine ecosystems around the world, although losses of global mangrove area have been occurring over the past decades. Therefore, tracking spatio-temporal changes and assessing the current state are essential for mangroves conservation. To solve the issues of inaccurate detection results of single algorithms and those limited to historical change detection, this study proposes the detect–monitor–predict (DMP) framework of mangroves for detecting time-series historical changes, monitoring abrupt near-real-time events, and predicting future trends in Beibu Gulf, China, through the synergetic use of multiple detection change algorithms. This study further developed a method for extracting mangroves using multi-source inter-annual time-series spectral indices images, and evaluated the performance of twenty-one spectral indices for capturing expansion events of mangroves. Finally, this study reveals the spatio-temporal dynamics of mangroves in Beibu Gulf from 1986 to 2021. In this study, we found that our method could extract mangrove growth regions from 1986 to 2021, and achieved 0.887 overall accuracy, which proved that this method is able to rapidly extract large-scale mangroves without field-based samples. We confirmed that the normalized difference vegetation index and tasseled cap angle outperform other spectral indexes in capturing mangrove expansion changes, while enhanced vegetation index and soil-adjusted vegetation index capture the change events with a time delay. This study revealed that mangrove changes displayed historical changes in the hierarchical gradient from land to sea with an average annual expansion of 239.822 ha in the Beibu Gulf during 1986–2021, detected slight improvements and deteriorations of some contemporary mangroves, and predicted 72.778% of mangroves with good growth conditions in the future.

Corrigendum to “A procedure for the detection of undocumented multiple abrupt changes in the mean value of daily temperature time series of a regional network”

Corrigendum to “A procedure for the detection of undocumented multiple abrupt changes in the mean value of daily temperature time series of a regional network”

Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning

This study is concerned with urban change detection and categorization in point clouds. In such situations, objects are mainly characterized by their vertical axis, and the use of native 3D data such as 3D Point Clouds (PCs) is, in general, preferred to rasterized versions because of significant loss of information implied by any rasterization process. Yet, for obvious practical reasons, most existing studies only focus on 2D images for change detection purpose. In this paper, we propose a method capable of performing change detection directly within 3D data. Despite recent deep learning developments in remote sensing, to the best of our knowledge there is no such method to tackle multi-class change segmentation that directly processes raw 3D PCs. Thereby, based on advances in deep learning for change detection in 2D images and for analysis of 3D point clouds, we propose a deep Siamese KPConv network that deals with raw 3D PCs to perform change detection and categorization in a single step. Experimental results are conducted on synthetic and real data of various kinds (LiDAR, multi-sensors). Tests performed on simulated low density LiDAR and multi-sensor datasets show that our proposed method can obtain up to 80% of mean of IoU over classes of changes, leading to an improvement ranging from 10% to 30% over the state-of-the-art. A similar range of improvements is attainable on real data. Then, we show that pre-training Siamese KPConv on simulated PCs allows us to greatly reduce (more than 3,000×) the annotations required on real data. This is a highly significant result to deal with practical scenarios. Finally, an adaptation of Siamese KPConv is realized to deal with change classification at PC scale. Our network overtakes the current state-of-the-art deep learning method by 23% and 15% of mean of IoU when assessed on synthetic and public Change3D datasets, respectively. The code is available at the following link: https://github.com/IdeGelis/torch-points3d-SiameseKPConv.

Automatic 3D Multiple Building Change Detection Model Based on Encoder–Decoder Network Using Highly Unbalanced Remote Sensing Datasets

Automatic 3D Multiple Building Change Detection Model Based on Encoder–Decoder Network Using Highly Unbalanced Remote Sensing Datasets

A novel unsupervised multiple change detection method for VHR remote sensing imagery using CNN with hierarchical sampling

ABSTRACT Detecting multiple changes from remote sensing imagery is a research hotspot. Very high resolution (VHR) images contain detailed spatial information and thus are often used in multiple change detection (CD). Compared with supervised multiple CD methods, unsupervised methods are more attractive, due to the ability of extracting changes automatically. However, many existing unsupervised methods fail to well adaptively make use of the high-level features relevant to multiple changes in VHR images in some cases. In this paper, a novel unsupervised multiple CD method for VHR images is proposed. First, the magnitude of spectral change vectors (SCVs) is calculated by change vector analysis, and fuzzy c-means clustering is performed to generate the unchanged and candidate changed samples. Secondly, the candidate changed samples are further clustered based on the direction of SCVs, and multiple changed samples are selected using a local window. Finally, image patches composed of neighbourhood areas of the generated samples are fed into a convolutional neural network (CNN) for training, and the multiple change map is obtained by the trained CNN. Experiments were performed on four data sets, and results indicated that the proposed unsupervised multiple CD approach outperformed some other state-of-the-art methods.

A novel multiple change detection approach based on tri-temporal logic-verified change vector analysis in posterior probability space

• TLCVAPS gets rid of the dependence on change class information that contained in training samples, reducing the cost of sample acquisition in multiple change detection problems. • TLCVAPS avoids the error accumulation caused by comparing classification results at different dates for change trajectory detection. • TLCVAPS is the first attempt to introduce temporal logic into multiple change detection tasks, which is a pilot research for the utilization of time information. Detailed land cover change trajectory offers a better opportunity for understanding the dynamic of land surface process. However, change information contained in training samples, which are usually difficult to obtain, needs to be provided in advance to achieve such goal within a complex scenario. A novel multiple change detection approach, namely Tri-temporal Logic-verified Change Vector Analysis (TLCVA) in posterior Probability Space (TLCVAPS), was proposed in this paper. It removes the dependence on change class information contained in training samples, while reducing the detection errors by taking change logic into account for the first time. The proposed approach consists of three steps, including: (1) change vector produced in posterior probability space, (2) binary change detection via TLCVA, and (3) change trajectory identification through combining change vector angle comparison and logic verification in change pattern. We applied the proposed approach on three tri-temporal datasets obtained in Nanjing, Xianning, and Zhenjiang, China, respectively. The results confirmed the superiority of TLCVAPS in comparison with state-of-the-art multiple change detection methods with the same prior knowledge.

GREPore-seq: A Robust Workflow to Detect Changes After Gene Editing Through Long-range PCR and Nanopore Sequencing

To achieve the enormous potential of gene-editing technology in clinical therapies, one needs to evaluate both the on-target efficiency and unintended editing consequences comprehensively. However, there is a lack of a pipelined, large-scale, and economical workflow for detecting genome editing outcomes, in particular insertion or deletion of a large fragment. Here, we describe an approach for efficient and accurate detection of multiple genetic changes after CRISPR/Cas9 editing by pooled nanopore sequencing of barcoded long-range PCR products. Recognizing the high error rates of Oxford nanopore sequencing, we developed a novel pipeline to capture the barcoded sequences by grepping reads of nanopore amplicon sequencing (GREPore-seq). GREPore-seq can assess nonhomologous end-joining (NHEJ)-mediated double-stranded oligodeoxynucleotide (dsODN) insertions with comparable accuracy to Illumina next-generation sequencing (NGS). GREPore-seq also reveals a full spectrum of homology-directed repair (HDR)-mediated large gene knock-in, correlating well with the fluorescence-activated cell sorting (FACS) analysis results. Of note, we discovered low-level fragmented and full-length plasmid backbone insertion at the CRISPR cutting site. Therefore, we have established a practical workflow to evaluate various genetic changes, including quantifying insertions of short dsODNs, knock-ins of long pieces, plasmid insertions, and large fragment deletions after CRISPR/Cas9-mediated editing. GREPore-seq is freely available at GitHub (https://github.com/lisiang/GREPore-seq) and the National Genomics Data Center (NGDC) BioCode (https://ngdc.cncb.ac.cn/biocode/tools/BT007293).

Unsupervised Multiple Change Detection for Multispectral Images Based on AMMF and SpatioSpectral Channel Augmentation

Due to the difficulty and time-consuming of labeling ground truth map in practical situations, unsupervised multiple change detection (MCD) for multispectral images (MSIs) have attracted much attention in recent years. One possible strategy to obtain multiple changes is to assign labels to the binary change result. However, some methods are difficult to obtain the accurate binary result because of the complexity of backgrounds; moreover, assigning labels is also a challenge owing to the limitation of the number of spectral channels in MSIs. Therefore, we propose a novel unsupervised MCD framework based on auto-updating multitemporal matrix factorization (AMMF) and spatiospectral channel augmentation (SSCA). In AMMF, the accurate binary change result can be detected based on joint matrix factorization, during which the distribution and subspace information of each temporal image are regularized to encode the spatiotemporal correlation. In SSCA, some novel augmentation strategies are introduced to increase the number of channels in MSIs to form the normalized high-dimensional maps for each temporal image based on nonlinear operations and convolutional sparse analysis, respectively. MCD can be achieved by integrating the binary change result and directional information that can be calculated by high-dimensional maps of different temporal images. Experiments are conducted on two real MSIs, indicating that the proposed framework performs well in detecting multiple changes.

Unsupervised Multiple Change Detection in Remote Sensing Images via Generative Representation Learning Network

With abundant temporal, spectral, and spatial information, multispectral images are proficient for acquiring a superior comprehension of the Earth’s condition and its changes, which enables the achievement of multiple change detection (CD) tasks. However, high temporal, spatial, and spectral information of data brings obstacles to perform multiple change analysis due to the lack of effective feature extraction operation. In addition, the traditional multiple CD methods rely too much on manual participation. Here, a generative representation learning network (GRN) and a cyclic clustering technique are combined into a unified model, which is driven to learn spatial–temporal–spectral features for unsupervised multiple CD. GRN aims to efficiently extract and merge robust difference information with a recurrent learning mechanism for self-adaptive classification refinement, in which different types of changes can be identified and highlighted. Furthermore, a cyclic training strategy is designed to refine the clustering-friendly features, in which similar change types are gradually merged into the same classes. Meanwhile, the number of change types will be optimized through a self-adaptive way and eventually converge to its stable state, which is close to the real distribution. Experimental results on real multispectral datasets demonstrate the effectiveness and superiority of the proposed model on multiple CD.

WH-MAVS: A Novel Dataset and Deep Learning Benchmark for Multiple Land Use and Land Cover Applications

Over the past decade, many excellent data sharing efforts have enriched the remote sensing scene classification (SC) methods. These datasets have achieved great success in complex high-level semantic information interpretation. However, most existing datasets are collected from standard and ungeoreferenced image patches for algorithm training and evaluation. These datasets do not fit for practical applications and cannot be directly applied in further geographical study. Accordingly, we provide a large range high-resolution SC dataset with multiple time phases, called “ <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">W</b> u <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">h</b> an <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> ulti <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</b> pplication <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</b> HR <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> cene classification dataset (WH-MAVS).” It facilitates the study of SC and scene change detection (SCD) algorithms. Moreover, it can also be directly employed to perform a variety of real-life land use application tasks. To the best of our knowledge, this is the first free, publicly available, georeferenced, and annotated dataset to cover almost an entire megacity. The WH-MAVS was collected and annotated from Google Earth imagery with the same spatial resolution and uniform nonoverlapping patch size, covering the central area of Wuhan, China. The total number of scene samples is 47 137, which belong to 14 classes with 23 567 labeled patches for each time phase in 2014 and 2016, respectively. The geographic coordinates of all samples in both time phases exhibit one-to-one correspondence with 23 202 unchanged image patches of scene categories and 365 changed ones. The distribution of the number of samples in each class is highly imbalanced; moreover, there are large intraclass differences and indistinguishable interclass variances. These characteristics are closer to the real land use/land cover application tasks and introduce further challenges to the related algorithm research. In addition, we conducted benchmark experiments on SC and SCD based on the WH-MAVS dataset with widely used deep learning models. DenseNet169 was found to achieve the best performance. The overall accuracies are 91.07% and 92.09%, respectively, in the 2014 and 2016 validation sets of WH-MAVS. Furthermore, SCD obtained by DenseNet169 has a binary change detection accuracy of 89.56% and a multiple (from–to) change detection accuracy of 86.70%. Over and above the research value of the algorithm, it is also proven to have practical applications in fields such as urban planning, landscape pattern analysis, and urban dynamic monitoring and analysis.

A New Structure for Binary and Multiple Hyperspectral Change Detection Based on Spectral Unmixing and Convolutional Neural Network

The earth is constantly being changed by natural events and human activities that constantly threaten our environment. Therefore, accurate and timely monitoring of changes at the surface of the earth is of great importance for properly facing their consequences. This research presents a new hyperspectral change detection (HCD) framework based on a robust binary mask and convolutional neural network (CNN). The proposed method is implemented in three parts: (1) the first part provides a robust binary change map based on Otsu and dynamic time wrapping (DTW) algorithms; the DTW algorithm plays a predictor role that is a robust predictor for HCD purposes. Also, Otsu’s algorithm gives an estimate about the approximate threshold for detecting change and no-change class areas. These class areas will be used in the next steps. (2) The second part generates pseudo training data based on an image differencing (ID) algorithm and spectral unmixing (SU) manner for multiple change detection. This pseudo training data will be used for training the CNN model in the next step. (3) Finally, the multiple change map is generated by training the CNN network based on pseudo training data. The result of HCD maps is compared to other robust hyperspectral change detection methods by two real bi-temporal hyperspectral image datasets. The result of HCD in multiple change map shows the proposed method can have high performance compared to other HCD methods with an overall accuracy (OA) of more than 92% and Kappa coefficient (KC) of 0.77 and higher.

Motion disrupts dynamic visual search for an orientation change

Visual search in dynamic environments, for example lifeguarding or CCTV monitoring, has several fundamentally different properties to standard visual search tasks. The visual environment is constantly moving, a range of items could become targets and the task is to search for a certain event. We developed a novel task in which participants were required to search static and moving displays for an orientation change thus capturing components of visual search, multiple object tracking and change detection paradigms. In Experiment 1, we found that the addition of moving distractors slowed participants’ response time to detect an orientation changes in a moving target, showing that the motion of distractors disrupts the rapid detection of orientation changes in a moving target. In Experiment 2 we found that, in displays of both moving and static objects, response time was slower if a moving object underwent a change than if a static object did, thus demonstrating that motion of the target itself also disrupts the detection of an orientation change. Our results could have implications for training in real-world occupations where the task is to search a dynamic environment for a critical event. Moreover, we add to the literature highlighting the need to develop lab-based tasks with high experimental control from any real-world tasks researchers may wish to investigate rather than extrapolating from static visual search tasks to more dynamic environments.

Update on Diagnosis of Childhood Acute Lymphoblastic Leukemia (ALL) in Indonesia

Update on Diagnosis of Childhood Acute Lymphoblastic Leukemia (ALL) in Indonesia

Automated detection of multiple structural changes of diabetic macular oedema in SDOCT retinal images through transfer learning in CNNs

Diabetic Maculopathy, the major cause of vision loss, occurs due to uncontrolled diabetes. This affects the retinal layers of the eye causing bleeding of vessels, which results in Diabetic Macular Edema (DME), macular detachment etc., Basically three structural changes are involved in DME viz., Cystoid Macular Edema (CME), Serous Macular Detachment (SMD) and Intra Retinal Fluid (IRF). These changes may also coexist with each other such as CME with SMD or CME with IRF etc. In this work, the retinal images acquired through Spectral Domain Optical Coherence Tomography (SDOCT) imaging modality, which would provide high level of precision and resolution of the retinal layers are utilized. An automated algorithm to detect and differentiate seven types of DME based on deep learning is implemented using transfer learning on three Convolutional Neural Networks (CNNs), ResNet 50, VGGNet and AlexNet. In detection of DME, ResNet 50 performs excellently well, when compared with Alexnet and VGGNet, because of its depth and skip connection features. The average values of the statistical parameters such as accuracy (0.993), F1 score (0.975), Mathews Correlation Coefficient(MCC)(0.972) of ResNet are high when compared to that of AlexNet and VGGNet

Using Adversarial Network for Multiple Change Detection in Bitemporal Remote Sensing Imagery

Change detection by comparing two bitemporal images is one of the most challenging tasks in remote sensing. At present, most related studies focus on change area detection while neglecting multiple change type identification. In this letter, an attention gates generative adversarial adaptation network (AG-GAAN) is proposed on multiple change detection. The AG-GAAN has the following contributions: 1) this method can automatically detect multiple changes; 2) it includes attention gates mechanism for spatial constraint and accelerates change area identification with finer contours; and 3) the domain similarity loss is introduced to improve the discriminability of the model so that the model can map out real changes more accurately. To demonstrate the robustness of this approach, we used the Google Earth data sets that include seasonal variations for change detection and understanding. The experimental results demonstrated that the proposed method can accurately detect the multiple change types from bitemporal imagery.

Hyperspectral multiple-change detection framework based on sparse representation and support vector data description algorithms

Change detection of hyperspectral (HS) images can be a motivating research area because of the dense spectral sampling of the HS dataset. The support vector domain description (SVDD) classifier has been widely used for change detection of multispectral images. Most of the research has focused only on the binary change detection problem. We took advantage of the high spectral resolution of HS images to extract different kinds of changes present in the image. As a result, we proposed a multiple-change detection algorithm for the HS dataset based on the sparse representation binary change mask and SVDD classifiers. Also, a geometric index, D2R2, was presented to integrate the binary SVDD classifiers. The experimental results showed that our proposed algorithm has comparable performance to some deep neural networks, including one-dimensional convolutional neural network (CNN), two-dimensional CNN, and Deep Pattern Net, with overall accuracies of 88.51% and 70.11% on the two Hyperion sensor datasets.

Nonparametric change point detection for periodic time series

AbstractWe consider detection of multiple changes in the distribution of periodic and autocorrelated data with known period. To account for periodicity we transform the sequence of vector observations by arranging them in matrices and thereby producing a sequence of independently and identically distributed matrix observations. We propose methods of testing the equality of matrix distributions and present methods that can be applied to matrix observations using the E‐divisive algorithm. We show that periodicity and autocorrelation degrade existing change detection methods because they blur the changes that these procedures aim to discover. Methods that ignore the periodicity have low power to detect changes in the mean and the variance of periodic time series when the periodic effects overwhelm the true changes, while the proposed methods detect such changes with high power. We illustrate the proposed methods by detecting changes in the water quality of Lake Kasumigaura in Japan. The Canadian Journal of Statistics 48: 518–534; 2020 © 2020 Statistical Society of Canada

An Unsupervised Binary and Multiple Change Detection Approach for Hyperspectral Imagery Based on Spectral Unmixing

Over the last decade, developments in hyperspectral sensors have caused an increase in the use of hyperspectral images (HSIs) due to fine spectral resolution, which has lead to the precise extraction and identification of the materials of the observed scene. Change detection (CD) is one of the most fundamental applications of remote sensing, which provides timely change information about Earth's surface. This article presents unsupervised binary and multiple CD approaches using bitemporal HSIs based on spectral unmixing (SU) and proposes a new formulation for CD without using threshold selection methods. SU is a powerful technique for analyzing hyperspectral data. CD, by incorporating unmixing, has the potential to obtain subpixel-level information from data. The proposed framework is organized in the context of four steps: Step 1) estimating the number of endmembers, extracting the endmember's signature, calculating abundances, and applying similarity assessment to identify corresponding endmembers; Step 2) discriminating pure changed pixels; Step 3) discriminating mixed changed pixels, and combining results by pure changed pixels to produce a binary change map (BCM); and Step 4) labeling changed pixels based on the proposed formulation and producing a multiple change map. This article presents new strategies for binary and multiple CD, which provide a better figure of merit as they do not need the threshold selection methods and are less time-consuming. The experiments on real hyperspectral datasets revealed that both CD accuracy and computational performance benefited from these strategies. Experimental results proved the high performance of the proposed approaches for detecting changes in both binary and multiple cases.